Related Experiment Video
Updated: Sep 3, 2025
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
A Novel Method for Lung Image Processing Using Complex Networks.
Laura Broască1, Ana Adriana Trușculescu2,3, Versavia Maria Ancușa1
1Department of Computer and Information Technology, Automation and Computers Faculty, "Politehnica" University of Timișoara, Vasile Pârvan Blvd. No. 2, 300223 Timișoara, Romania.
This study introduces a novel complex network approach for analyzing High-Resolution Computed Tomography (HRCT) scans to detect diffuse interstitial lung diseases (DILD). The method objectively quantifies lung disease features, improving diagnosis accuracy.
Area of Science:
- Radiology
- Medical Imaging
- Network Science
Background:
- Diffuse interstitial lung diseases (DILD) diagnosis relies on High-Resolution Computed Tomography (HRCT) findings, clinical data, and patient history.
- Current HRCT analysis for DILD often involves subjective interpretation of limited findings and patterns.
Purpose of the Study:
- To implement and evaluate a complex network approach for objective quantification of DILD from HRCT images.
- To translate HRCT lung imaging into complex networks for detailed pathological analysis.
Main Methods:
- The proposed method processes HRCT images by sampling secondary lobules and converting them into complex networks.
- Analysis is performed in three dimensions, focusing on emphysema, ground glass opacity, and consolidation.
- The technique was validated on a cohort of 60 patients.
Main Results:
- The complex network analysis demonstrated a clear, quantifiable distinction between healthy and diseased lungs.
- The method provides an objective approach to characterizing DILD features previously assessed subjectively.
Conclusions:
- This complex network-based technique offers a promising objective method for the diagnosis and quantification of DILD using HRCT.
- The approach has the potential to enhance the accuracy and consistency of DILD assessment in clinical practice.
